Struct HistGradientBoostingRegressor 

pub struct HistGradientBoostingRegressor<F> {
    pub n_estimators: usize,
    pub learning_rate: f64,
    pub max_depth: Option<usize>,
    pub min_samples_leaf: usize,
    pub max_bins: u16,
    pub l2_regularization: f64,
    pub max_leaf_nodes: Option<usize>,
    pub loss: HistRegressionLoss,
    pub random_state: Option<u64>,
    /* private fields */
}

Histogram-based gradient boosting regressor.

Uses quantile-based feature binning and gradient/hessian histograms for O(n_bins) split finding per node. This is significantly faster than the standard GradientBoostingRegressor for larger datasets.

Type Parameters

• F: The floating-point type (f32 or f64).

Fields

n_estimators: usize

Number of boosting stages (trees).

learning_rate: f64

Learning rate (shrinkage) applied to each tree’s contribution.

max_depth: Option<usize>

Maximum depth of each tree.

min_samples_leaf: usize

Minimum number of samples required in a leaf node.

max_bins: u16

Maximum number of bins for feature discretisation (at most 256).

l2_regularization: f64

L2 regularization term on weights.

max_leaf_nodes: Option<usize>

Maximum number of leaf nodes per tree (best-first growth). If None, depth-first growth is used with max_depth.

loss: HistRegressionLoss

Loss function.

random_state: Option<u64>

Random seed for reproducibility.

Implementations

impl<F: Float> HistGradientBoostingRegressor<F>

pub fn new() -> Self

Create a new HistGradientBoostingRegressor with default settings.

Defaults: n_estimators = 100, learning_rate = 0.1, max_depth = None, min_samples_leaf = 20, max_bins = 255, l2_regularization = 0.0, max_leaf_nodes = Some(31), loss = LeastSquares.

pub fn with_n_estimators(self, n: usize) -> Self

Set the number of boosting stages.

pub fn with_learning_rate(self, lr: f64) -> Self

Set the learning rate (shrinkage).

pub fn with_max_depth(self, d: Option<usize>) -> Self

Set the maximum tree depth.

pub fn with_min_samples_leaf(self, n: usize) -> Self

Set the minimum number of samples in a leaf.

pub fn with_max_bins(self, bins: u16) -> Self

Set the maximum number of bins for feature discretisation.

pub fn with_l2_regularization(self, reg: f64) -> Self

Set the L2 regularization term.

pub fn with_max_leaf_nodes(self, n: Option<usize>) -> Self

Set the maximum number of leaf nodes (best-first growth).

pub fn with_loss(self, loss: HistRegressionLoss) -> Self

Set the loss function.

pub fn with_random_state(self, seed: u64) -> Self

Set the random seed for reproducibility.

Trait Implementations

impl<F: Clone> Clone for HistGradientBoostingRegressor<F>

fn clone(&self) -> HistGradientBoostingRegressor<F>

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<F: Debug> Debug for HistGradientBoostingRegressor<F>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<F: Float> Default for HistGradientBoostingRegressor<F>

fn default() -> Self

Returns the “default value” for a type.

impl<'de, F> Deserialize<'de> for HistGradientBoostingRegressor<F>

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl<F: Float + Send + Sync + 'static> Fit<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>> for HistGradientBoostingRegressor<F>

fn fit( &self, x: &Array2<F>, y: &Array1<F>, ) -> Result<FittedHistGradientBoostingRegressor<F>, FerroError>

Fit the histogram-based gradient boosting regressor.

Errors

Returns FerroError::ShapeMismatch if x and y have different numbers of samples. Returns FerroError::InsufficientSamples if there are no samples. Returns FerroError::InvalidParameter for invalid hyperparameters.

type Fitted = FittedHistGradientBoostingRegressor<F>

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.

impl<F: Float + Send + Sync + 'static> PipelineEstimator<F> for HistGradientBoostingRegressor<F>

fn fit_pipeline( &self, x: &Array2<F>, y: &Array1<F>, ) -> Result<Box<dyn FittedPipelineEstimator<F>>, FerroError>

Fit this estimator on the given data.

impl<F> Serialize for HistGradientBoostingRegressor<F>

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.